MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.

/pdf/computer-aided-diagnosis-in-chest-radiography-a-survey-2g53b77kmg.pdf

Computer-aided diagnosis in chest radiography: a survey

PURPOSE: To measure the effective radiation doses delivered at electron-beam computed tomography (CT) and multi–detector row spiral CT of coronary arteries and to compare these doses with those delivered at catheter coronary angiography. MATERIALS AND METHODS: An anthropomorphic phantom equipped with 66 thermoluminescent dosimeters was imaged at cardiac CT. Four protocols for unenhanced coronary artery calcium scoring were simulated: one with electron-beam CT and three with multi–detector row CT. Four similar protocols for coronary CT angiography were simulated. All multi–detector row spiral CT protocols were performed with retrospective electrocardiographic triggering. Biplane catheter coronary angiography also was simulated. Radiation doses to organs were measured, and effective doses were calculated according to guidelines published in International Commission on Radiological Protection Publication 60. RESULTS: Coronary artery calcium scoring with electron-beam CT yielded effective radiation doses of 1...

Radiation exposure during cardiac CT: effective doses at multi-detector row CT and electron-beam CT.

CT angiography (CTA) is based on acquisition of data during the arterial phase of contrast material passage. CTA needs timing of the contrast bolus, which should be based on accurate knowledge of bolus geometry. Experimental and human studies on bolus geometry and bolus timing in CTA were reviewed. Important parameters of bolus geometry and methods of bolus timing (test bolus and bolus tracking) are described. Recommendations are given for an optimal CTA protocol.

Parameters affecting bolus geometry in CTA: a review.

OBJECTIVE. Accurate assessment of lymph node status before treatment is critical in the treatment of gynecologic cancers because the 5-year survival and treatment of women is influenced by lymph node involvement. The aims of this study were to investigate the ability of X-ray CT, MR imaging, and 18F-FDG positron emission tomography (PET) to detect pelvic lymph node metastases by comparing imaging with histopathologic findings after lymph node dissection.MATERIALS AND METHODS. Eighteen patients with gynecologic cancers were studied by all three imaging methods before surgery. The images were initially reviewed with routine diagnostic conditions and then, subsequently, by two observers who were unaware of the clinical and histopathologic findings of the patients. The nodal sites were split into upper (aortic to common iliac bifurcations) and lower (common iliac bifurcations to inguinal ligament) iliac chains. All observers' results were statistically analyzed with specificity, sensitivity, positive and nega...

Detection of pelvic lymph node metastases in gynecologic malignancy: a comparison of CT, MR imaging, and positron emission tomography.

Objective: To develop an injection protocol for intravenous administration of contrast media in abdominal and pelvic helical CT which provides optimal contrast enhancement of arterial and venous vessels.Material and Methods: for the study on a Somatom Plus 4 unit, a standard helical CT examination procedure of abdomen and pelvis consisted firstly of a native helical examination of the liver, a second one of the liver after intravenous injection of 120 ml nonionic contrast medium with a constant start delay of 50 s, and subsequently a third helical CT of the lower abdomen and pelvis. 125 patients were randomized for examination under different protocols, varying the injection flow from 2.0–4.0 ml/s and the time delay between the second and the third helical examinations from an additional 20–40 s. the efficacy of the contrast injection was checked by region of interest (ROI) measurements of HUs in aorta, inferior vena cava, and in femoral arteries and veins. the results were compared by t-test statistics.R...

Prospective randomized study for an injection protocol for intravenous contrast media in abdominal and pelvic helical ct

PURPOSE To examine the extent to which digital luminescence radiography (DLR) can be used for the imaging of pulmonary nodules and interstitial lung disease in chest radiography without any loss of image quality. Additionally: to examine whether post-processing of image data can optimise the recognizability of varied image details. MATERIALS AND METHODS Detail perceptibility studies were performed on an anthropomorphic thorax phantom with simulated nodules and small linear and reticular details. Under standard conditions, digital luminescence radiographs were obtained in 7 different image modes, and these were compared with a 200-speed screen-film system. The detection of these systems was evaluated in an ROC analysis on the basis of 19,200 individual observations. RESULTS Edge enhancement or application of high-frequency-enhancing small filter kernels (S 5) slightly improves the detection of linear structures; however, the illustration of nodular details is markedly reduced. Larger filter kernels (S 20, S 40) make a definitive detection possible--not only of circular, but also of linear details. CONCLUSIONS Storage phosphor radiographs are equal to the tested analog screen-film-system. The optimization of post-processing can be helpful in the prevention of routine multiple documentations.

ROC-Analyse zur Bildnachverarbeitung digitaler Thoraxaufnahmen

170 patients who had suffered trauma to bones or soft tissues were examined by a digital and a conventional film/screen technique. In addition to "standard" and edge-enhanced images, post-processing was carried out and compared with conventional radiographs. Four radiologists and two surgeons evaluated the compacta, spongiosa, soft tissues, fractures and osteo-synthetic materials as shown on the two systems. The "standard" digital images are inferior to film images, but edge-enhanced images showed definite advantages for demonstrating soft tissues. Evaluation of osteo-synthetic material is limited by the creation of artifacts. Recognition of detail can be significantly improved by using post-processing with optimized parameters.

Digitale Lumineszenzradiographie (DLR) zur Skelettdiagnostik in der Traumatologie

The extent to which the diagnostic performance of low-dosed storage phosphors can be improved by suitable image postprocessing was investigated. Storage phosphors radiographs and conventional 200- and 400-speed screen-film combinations of an antropomorphic chest phantom with simulated nodules and linear structures were compared. The detection of test bodies was determined in an ROC analysis based on 16 200 individual observations. The two analog screen-film systems did not differ significantly. As far as the storage phosphor radiographs are concerned, a higher diagnostic performance was achieved with a large filter kernel (S 40), whereas small filter kernels and edge-enhanced imaging modes reduced the detection of detail. The image quality of low-dosed storage phosphors is thus similar to high-amplification screen-film combinations if large filter kernels are used in postprocessing of the image.

Unsharp masking of low-dosed digital luminiscence radiographs: results of a receiver operating characteristics analysis

PURPOSE The purpose of this study was to evaluate the efficacy of MRI with superparamagnetic iron oxide (SPIO) and double-spiral CT in the detection of liver metastases and hepatocellular carcinoma. METHODS 38 patients with a total of 144 malignant hepatic lesions underwent CT and MRI. A panel of experts defined the gold standard. Five experienced judges performed independently blinded evaluation of the number of detectable lesions. Multifactorial variance analysis was used to determine the statistical significance. RESULTS SPIO-MRI shows the highest rate of detection and is significantly superior to native MRI and native CT. The highest rate of detection by CT is shown in the portal-venous phase of contrast; nevertheless, the rate is significantly inferior to SPIO-MRI. In general, the native phases of CT and MRI are significantly inferior to the contrast phases of both. SPIO-MRI shows a higher rate of false positive findings. CONCLUSION The time-consuming and cost-intensive SPIO-MRI significantly increases the rate of detectability for malignant liver lesions compared with double-spiral CT but it also increases the rate of false positive findings.

R.-D. Müller

Papers

Prospective randomized study for an injection protocol for intravenous contrast media in abdominal and pelvic helical ct

ROC-Analyse zur Bildnachverarbeitung digitaler Thoraxaufnahmen

Digitale Lumineszenzradiographie (DLR) zur Skelettdiagnostik in der Traumatologie

Unsharp masking of low-dosed digital luminiscence radiographs: results of a receiver operating characteristics analysis

MRT mit superparamagnetischen Eisenpartikeln versus Doppelspiral-CT beim Nachweis maligner Leberläsionen